光流处理方法

光流处理工具
光流可视化工具

从光流估计网络输出光流

光流估计网络

LiteFlowNet2
GeoNet 光流深度位姿联合估计
Nvidia flownet2 pytorch
PWC-Net

光流保存为 png,jpg,flo 文件

			pre_flow = model(data )
# save flow
            flow_fn = '%.6d.png' % tgt_idx
            color_fn    = os.path.join(color_dir, flow_fn)
            color_flow  = fl.flow_to_image(pred_flow)
            color_flow  = cv2.cvtColor(color_flow, cv2.COLOR_RGB2BGR)
            color_flow  = cv2.imwrite(color_fn, color_flow)

            png_fn      = os.path.join(png_dir, flow_fn)
            mask_blob   = np.ones((opt.img_height, opt.img_width), dtype = np.uint16)
            fl.write_kitti_png_file(png_fn, pred_flow, mask_blob)

            binary_fn   = flow_fn.replace('.png', '.flo')
            binary_fn   = os.path.join(binary_dir, binary_fn)
            fl.write_flow(pred_flow, binary_fn)